numen-tech
/

Meta-Llama-3.1-70B-Instruct-w4a16g128asym

Model card Files Files and versions Community

Meta-Llama-3.1-70B-Instruct-w4a16g128asym / README.md

numen-tech's picture

Add weights

8f7b49d 6 months ago

|

history blame contribute delete

199 Bytes

	---
	license: llama3.1
	---

	4-bit [OmniQuant](https://arxiv.org/abs/2308.13137) quantized version of [Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct).